Exploring the Impact of Omitting Covariates Interaction Effect in Multilevel Multiple Indicators, Multiple Causes (MIMIC) Models

• In Event: Methods for Multilevel, Categorical, and Multidimensional Data

Abstract

Multilevel MIMIC models possess the flexibility of simultaneously modeling covariates at the between level and at the within level, as well interaction effects of the covariates. The interaction effect can be between level interaction, within level interaction, and cross-level interaction. This study investigates the impact of omitting the interaction on the estimate of other parameters when the covariates interaction effect is present in the population model. Moreover, the sensitivity of fit indices, such as chi-square, CFI, RMSEA, SRMR-B (between), and SRMR-W (within) are also examined. Results indicated that none of the fit indices was sensitive to the omission of the interaction effect. The biased parameter estimates included the two covariates main effect and the between-level factor mean.

Authors

• Chunhua Cao, The University of Alabama

• Eunsook Kim, University of South Florida

• Yi-Hsin Chen, University of South Florida

• John M. Ferron, University of South Florida